Speaker
Antoine Petitjean
(Heidelberg University)
Description
Modern machine learning is transforming jet tagging at the LHC, but the leading transformer architectures are large, not particularly fast, and training-intensive. We present a slim version of the L-GATr tagger, reduce the number of parameters of jet-tagging transformers, and quantize them. We compare different quantization methods for standard and Lorentz-equivariant transformers and estimate their gains in resource efficiency. We find an order-of-magnitude reduction in energy cost for an moderate performance decrease, down to 1000-parameter taggers. This might be a step towards trigger-level jet tagging with small and quantized versions of the leading equivariant transformer architectures.
Authors
Antoine Petitjean
(Heidelberg University)
Dr
Jonas Spinner
(Durham U., IPPP)
Tilman Plehn
Prof.
Ullrich Köthe
(IWR, Universität Heidelberg)